Model: None
Dataset: The Pile
Neuron 36 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2751. Min Act: -0.1700
Data Index: 4156898 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2751. Min Act: -0.1700
Data Index: 9720720 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2751. Min Act: -0.1700
Data Index: 107397 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2594. Min Act: -0.1700
Data Index: 8247160 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2437. Min Act: -0.1700
Data Index: 4973664 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2437. Min Act: -0.1700
Data Index: 3113345 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2437. Min Act: -0.1700
Data Index: 10334904 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2437. Min Act: -0.1700
Data Index: 7509728 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2437. Min Act: -0.1700
Data Index: 7121920 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2280. Min Act: -0.1700
Data Index: 9851394 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2280. Min Act: -0.1700
Data Index: 3903533 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2280. Min Act: -0.1700
Data Index: 1524892 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2122. Min Act: -0.1700
Data Index: 6698628 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2122. Min Act: -0.1700
Data Index: 1411091 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2122. Min Act: -0.1700
Data Index: 6137687 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.2122. Min Act: -0.1700
Data Index: 8603357 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.1965. Min Act: -0.1700
Data Index: 2744159 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.1965. Min Act: -0.1700
Data Index: 8285400 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.1965. Min Act: -0.1700
Data Index: 320977 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2751. Min Range: -3.2751
Max Act: 3.1965. Min Act: -0.1700
Data Index: 6340655 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19